RLTasksby ulam.ai
Models / DeepSeek

DeepSeek / MODEL EVIDENCE

DeepSeek-R1-Distill-Llama-70B

6 benchmarks · 11 observations · 6 sources · released 2025-01-20

Scores at a glance

6 benchmarks · large dot: DeepSeek-R1-Distill-Llama-70B; small dots: closest models where reported

GPQA Diamond ↗55.74%
9.2896.4

DeepSeek-R1-Distill-Llama-70B · GPQA diamond · Best score (across scorers) · % ↗

MATH Level 5 ↗89.9%
3.2998.13

DeepSeek-R1-Distill-Llama-70B · MATH level 5 · Best score (across scorers) · % ↗

LiveBench ↗54.5%
22.0882.35

DeepSeek-R1-Distill-Llama-70B · LiveBench · Global average · % ↗

LiveCodeBench Pro ↗999 Elo
1999

DeepSeek R1 Distill-Llama-70B · LiveCodeBench Pro · Elo rating · human contest calibration ↗

3 more reported results

0% · DeepSeek R1 Distill-Llama-70B · LiveCodeBench Pro · Hard · pass@1 · difficulty breakdown · LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? ↗

2.8% · DeepSeek R1 Distill-Llama-70B · LiveCodeBench Pro · Medium · pass@1 · difficulty breakdown · LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? ↗

33.8% · DeepSeek R1 Distill-Llama-70B · LiveCodeBench Pro · Easy · pass@1 · difficulty breakdown · LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? ↗

UGPhysics ↗45.96%
5.3657.16

DeepSeek-R1-Distill-Llama-70B · UGPhysics · English · overall accuracy · original evaluation ↗

2 more reported results

34.38% · DeepSeek-R1-Distill-Llama-70B · UGPhysics · Chinese · overall accuracy · original evaluation · UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models ↗

40.17% · DeepSeek-R1-Distill-Llama-70B · UGPhysics · Language average · overall accuracy · original evaluation · UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models ↗

Closest models by score

Similar positions on shared benchmark leaderboards. Smaller gaps are closer.

4.5 percentile-point gap

3 of 3 shared benchmark comparisons

5.7 percentile-point gap

3 of 3 shared benchmark comparisons

How similarity is measured

Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.

Filter comparisons to this model →

Sources

Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.

  1. UGPhysics: A Comprehensive Benchmark for Undergraduate Physics Reasoning with Large Language Models — published result table ↗

    Xin Xu, Qiyun Xu, Tong Xiao, Tianhao Chen, Yuchen Yan, Jiaxin Zhang et al. · 2025

    All 9 authors

    Xin Xu, Qiyun Xu, Tong Xiao, Tianhao Chen, Yuchen Yan, Jiaxin Zhang, Shizhe Diao, Can Yang, Yang Wang

  2. LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming? — published result table ↗

    Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He et al. · 2025

    All 19 authors

    Zihan Zheng, Zerui Cheng, Zeyu Shen, Shang Zhou, Kaiyuan Liu, Hansen He, Dongruixuan Li, Stanley Wei, Hangyi Hao, Jianzhu Yao, Peiyao Sheng, Zixuan Wang, Wenhao Chai, Aleksandra Korolova, Peter Henderson, Sanjeev Arora, Pramod Viswanath, Jingbo Shang, Saining Xie

  3. GPQA Diamond ↗

    Epoch AI

  4. MATH Level 5 ↗

    Epoch AI

  5. OTIS Mock AIME 2024-2025 ↗

    Epoch AI

  6. LiveBench — model evaluation leaderboard ↗

    LiveBench Team

Names used in source tables

DeepSeek R1 Distill-Llama-70B · DeepSeek-R1-Distill-Llama-70B